检索结果-内蒙古大学图书馆

Towards Leveraging Explainable Artificial Intelligent (XAI) in Requirements Engineering (RE) to Identify Aspect (Crosscutting Concern): A Systematic Literature Review (SLR) and Bibliometric Analysis

Towards Leveraging Explainable Artificial Intelligent (XAI) ...

引用

International Conference on information Technology (ICIT)

作者： Aws A. Magableh Department of Information Systems Faculty of Computer Science and Information Technology Yarmouk University Irbid Jordan

The software development life cycle contains many phases, among the most notable ones is requirements engineering (RE), it is considered a very important activity because poorly implemented RE steps can result in poor software quality which might lead to expensive maintenance costs and so many other undesirable issues. Thus, owing to the importance of RE in general and aspect (crosscutting concerns) identification in particular, researchers have proposed many approaches that can help to produce a clear and complete set of requirements document. On the other hand, artificial intelligence methods have a proven record of handling complicated text. Yet there is insufficient understanding of how AI and explainable AI can be employed and incorporated to be utilized in RE. Nevertheless, join forces to produce research for beneficial outcomes in this theme. The present study is a comprehensive SLR that reviewed the current state-of-the-art of AI/XAL in RE and aspect orientation. We reviewed the research from 2007 till 2022, PRISMA methodology is utilized to obtain a final set of (n =23) articles from four major scientific databases (Scopus, and Web of science). Clear and new taxonomies were invented during the review discussion. Additionally, to enhance the contribution of this research, a bibliometric comprehensive analysis was conducted on the basis of annual scientific production, country scientific production, and co-occurrence. As a result, it is deemed a noteworthy topic of extensive exploration especially after we identify critical research gaps with their corresponding solutions and generic thoughts to serve as a guide for future directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Software Tool for Fast Multiview Visualization of High-Dimensional Datasets 15th

A Novel Software Tool for Fast Multiview Visualization of ...

引用

15th International scientific conferences on research and applications in the field of intelligent information and database systems, ACIIDS 2023

作者： Zhang, Luying Tian, Hui Shen, Hong School of Computer Science Beijing Jiaotong University Beijing China School of Information and Communication Technology Griffith University Gold Coast Australia Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783031424298

Scatterplot is a popular technique for visualizing high-dimensional datasets by using linear and nonlinear dimension reduction methods. These methods map the original high-dimensional dataset onto scatterplot points directly by dimension reduction, and hence require a high computation cost. Despite many improvements in scatterplot visual effects, however, when the data volume is large, the data mapped onto scatterplot data points will overlap, resulting a low quality of visualization. In this paper, we propose a novel software tool that ensembles five integrated components for fast multiview visualization of high-dimensional datasets: sampling, dimension reduction, clustering, multiview collaborative analysis, and dimension re-arrangement. In our tool, while the sampling component reduces the sizes of the datasets applying the random sampling technique to gain a high visualization efficiency, dimension reduction reduces the dimensions of the datasets applying principal-component analysis to improve the visualization quality. Next, clustering discovers hidden information in the reduced dataset applying fuzzy c-mean clustering to display hidden patterns of the original datasets. Finally, multiview collaborative analysis enables users to analyse multidimensional datasets from different aspects at the same time by combining scatterplot and scatterplot matrices. To optimize the visualization effects, in the scatterplot matrices, we re-arrange their dimensions and adjust the positions of scatterplots so that similar scatterplot points are adjacent in positions. As the result, in comparison with the existing visualization tools that apply some of these techniques, our tool not only improves the efficiency of dimension reduction but also enhances the quality of visualization and enables more comprehensive analysis. We test our tool on different real datasets to demonstrate its effectiveness. The experimental results validate that our method is effective in both efficiency a

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Brain Cancer Tumor Classification from Motion-Corrected MRI Images Using Convolutional Neural Network

引用

computers, Materials & Continua 2021年第8期68卷 1551-1563页

作者： Hanan Abdullah Mengash Hanan A.Hosni Mahmoud Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Science College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer and Systems Engineering Faculty of EngineeringUniversity of AlexandriaAlexandriaEgypt

Detection of brain tumors in MRI images is the first step in brain cancer *** accuracy of the diagnosis depends highly on the expertise of ***,automated diagnosis of brain cancer from MRI is receiving a large amount of ***,MRI tumor detection is usually followed by a biopsy(an invasive procedure),which is a medical procedure for brain tumor *** is of high importance to devise automated methods to aid radiologists in brain cancer tumor diagnosis without resorting to invasive *** neural network(CNN)is deemed to be one of the best machine learning algorithms to achieve high-accuracy results in tumor identification and *** this paper,a CNN-based technique for brain tumor classification has been *** proposed CNN can distinguish between normal(no-cancer),astrocytoma tumors,gliomatosis cerebri tumors,and glioblastoma *** implemented CNN was tested on MRI images that underwent a motion-correction *** CNN was evaluated using two performance measurement *** first one is a k-fold cross-validation testing method,in which we tested the dataset using k=8,10,12,and *** best accuracy for this procedure was 96.26%when k=*** overcome the over-fitting problem that could be occurred in the k-fold testing method,we used a hold-out testing method as a second evaluation *** results of this procedure succeeded in attaining 97.8%accuracy,with a specificity of 99.2%and a sensitivity of 97.32%.With this high accuracy,the developed CNN architecture could be considered an effective automated diagnosis method for the classification of brain tumors from MRI images.

关键词： Classification convolutional neural network tumor classification MRI deep learning k-fold cross classification

来源：评论

学校读者我要写书评

暂无评论

Enhancement of High-Definition Map for Autonomous Vehicle Application by Light Intensity Equalization Technique

Enhancement of High-Definition Map for Autonomous Vehicle Ap...

引用

IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)

作者： Pattarapoom Nokkaew Nikorn Sutthisangiam Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350353464

ISBN: (纸本)9798350353471

This research aims to enhance point cloud data and simulate the operations of autonomous vehicles following data refinement. The study utilizes high-resolution point cloud data generated by a mobile mapping system and employs histogram equalization techniques to broaden the range of intensity levels, enhance contrast, and overall improve intensity values. The findings demonstrate a heightened density of dispersed intensity values and an expanded range of intensity levels compared to previous states. The point cloud data file size contribute to a 21% increase from additional shade values recording format, allows for clearer displays of road details and surrounding areas. while simultaneously increasing the accuracy of coordinates on these maps by 15%, as evaluated through simulations. Additionally, this process can aid in the creation of vector maps, a component of high-resolution maps for autonomous vehicles, thereby enhancing performance in various scenarios such as decision-making at intersections and obstacle detection.

关键词： Point cloud compression Histograms Accuracy Laser radar Roads Vectors Recording

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching 30

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

30th IEEE International Conference on Parallel and Distributed systems, ICPADS 2024

作者： Zhang, Yu Zhang, Jianqiang Song, Gongpeng Lu, Qin Zhao, Shuo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9798331515966

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method. © 2024 IEEE.

关键词： cross-modal retrieval feature enhancement image-text matching relationship interaction

来源：评论

学校读者我要写书评

暂无评论

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Similarity Computation Model Based on Optimised SBERT

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Simila...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Zhao, Shuo Gu, Qiliang Zhang, Jianqiang Song, Gongpeng Lu, Qin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9781665410205

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Novel Image Encryption and Compression Scheme for IoT Environment

引用

computers, Materials & Continua 2022年第4期71卷 1443-1457页

作者： Mesfer Al Duhayyim Fahd N.Al-Wesabi Radwa Marzouk Manar Ahmed Hamza Anwer Mustafa Hilal Majdy M.Eltahir Department of Natural and Applied Sciences College of Community-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversitySaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Latest advancements made in the processing abilities of smartdevices have resulted in the designing of Intelligent Internet of Things (IoT)environment. This advanced environment enables the nodes to connect, collect, perceive, and examine useful data from its surroundings. Wireless Multimedia Surveillance Networks (WMSNs) form a vital part in IoT-assistedenvironment since it contains visual sensors that examine the surroundingsfrom a number of overlapping views by capturing the images *** IoT devices generate a massive quantity of digital media, it is thereforerequired to save the media, especially images, in a secure way. In order toachieve security, encryption techniques as well as compression techniques areemployed to reduce the amount of digital data, being communicated overthe network. Encryption Then Compression (ETC) techniques pave a wayfor secure and compact transmission of the available data to prevent unauthorized access. With this background, the current research paper presentsa new ETC technique to accomplish image security in IoT *** proposed model involves three major processes namely, IoT-based imageacquisition, encryption, and compression. The presented model involves optimal Signcryption Technique with Whale Optimization Algorithm (NMWOA)abbreviated as ST-NMWOA. The optimal key generation of signcryptiontechnique takes place with the help of NMWOA. Besides, the presented modelalso uses Discrete Fourier Transform (DFT) and Matrix Minimization (MM)algorithm-based compression technique. Extensive set of experimental analysis was conducted to validate the effective performance of the proposed *** obtained values infer that the presented model is superior in terms of bothcompression efficiency and data secrecy in resource-limited IoT environment.

关键词： Data compression image security encryption signcryption optimal key generation

来源：评论

学校读者我要写书评

暂无评论

Addressing the Libyan Arabic Dialect Identification: A Comparative Study of Ensemble Classification Methods

Addressing the Libyan Arabic Dialect Identification: A Compa...

引用

sciences and Techniques of Automatic Control and computer Engineering MI-STA, IEEE International Maghreb Meeting of the Conference on

作者： Najah A. Ghumeid Mansour Essgaer Computer science department Faculty of Sciences Sebha University Sebha Libya Information Systems Department Faculty of Information Technology Sebha University Sebha Libya

ISBN: (数字)9798350372632

ISBN: (纸本)9798350372649

Dialect identification presents a challenging task within the realm of Natural Language Processing. The growing utilization of Arabic dialects in written form, particularly on social media platforms, has created new demands for accurate identification of these dialects. In multilingual datasets, distinguishing the Libyan Arabic dialect from neighboring Arabic dialects has emerged as a crucial goal. To address this, we conducted experiments using different lengths of word n-gram features to determine the most suitable combination of word n-grams and term frequency-inverse document frequency. Our aim was to capture contextual information effectively while mitigating linguistic similarities between Arabic dialects of neighboring countries. The QCRI Arabic Dialects Identification dataset was employed, and we evaluated the performance of three ensemble tree-based classification methods: Random Forest, Gradient Boost Machine, and eXtreme Gradient Boosting. The evaluation, based on the f-measure metric, yielded respective scores of 68%, 37%, and 52% for Random Forest, Gradient Boost Machine, and eXtreme Gradient Boosting. These results underscore the effectiveness of our approach in identifying the Libyan Arabic dialect and highlight the potential of ensemble tree-based methods in Arabic dialect identification tasks.

关键词： Measurement Automatic frequency control Accuracy Social networking (online) Linguistics Boosting Frequency diversity

来源：评论

学校读者我要写书评

暂无评论

White Leg Shrimp Larvae Counting System

White Leg Shrimp Larvae Counting System

引用

International Conference on Knowledge and Smart Technology (KST)

作者： Vutichai Kamthang Khantharat Anekboon Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

White leg shrimp is one of the animals that is popularly consumed and exported in Thailand. A lot of farmers cultivate white leg shrimp in many areas. To raise white leg shrimp larvae into mature white leg shrimp that can be sold in the market for further consumption or export. Before a farm sells white leg shrimp larvae to a farmer, the farm staff needs to count the number of them. The traditional counting method is naked-eye estimation which requires experience and gives a rough estimation. A traditional technique causes time- consuming and human error. Moreover, a farm usually adds some scoops to make sure that the number of white leg shrimp larvae is not less than an order. This situation affects the farm's costs. This study proposes a new system for automated counting white leg shrimp larvae by applying the simple blob detector technique with opening and closing of morphological operations. The experimental result of the proposed system shows that this proposed system gives the best accuracy (94.20%), precision (97.68%), recall (96.35%), and F1 score (96.98 % ) compared with Canny Edge Detection and Blob analysis, morphological operations (opening, dilatation and gamma correction), and the blue sense system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic speaker identification system based on MLP network and deep learning in the presence of severe interference

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Shafik, Amira Sedik, Ahmed El-Shafai, Walid Khalaf, Ashraf A. M. El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafr Elsheikh University Kafr El‑Shaikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Identification (ASI) is so crucial for security. Current ASI systems perform well in quiet and clean surroundings. However, in noisy situations, the robustness of an ASI system against additive noise and interference is a crucial factor. An investigation of the impact of interference on ASI system performance is presented in this paper, which introduces algorithms for achieving high ASI system performance. The objective is to resist the interference of various forms. This paper presents two models for the ASI task in the presence of interference. The first one depends on Normalized Pitch Frequency (NPF) and Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features and Multi-Layer Perceptron (MLP) as a classifier. In this model, we investigate the utilization of a Discrete Transform (DT), such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST), to increase the robustness of extracted features against different types of degradation through exploiting the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This is achieved by extracting features directly from contaminated speech signals in addition to features extracted from discrete transformed signals to create hybrid feature vectors. The enhancement techniques, such as Spectral Subtraction (SS), Winer Filter, and adaptive Wiener filter, are used in a preprocessing stage to eliminate the effect of the interference on the ASI system. In the second model, we investigate the utilization of Deep Learning (DL) based on a Convolutional Neural Network (CNN) with speech signal spectrograms and their Radon transforms to increase the robustness of the ASI system against interference effects. One of this paper goals is to introduce a comparison between the two models and build a more robust ASI system against severe interference. The experimental results indicate that the two proposed models lead to satisfa

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：